Leveraging state-of-the-art AI structure predictors to generate atomic resolution ensembles of intrinsically disordered proteins

bAIes generates atomistic conformational ensembles for intrinsically disordered proteins that match experimental NMR and SAXS accuracy and remain competitive with all-atom simulations across six structure predictors.

• Why it matters: IDP function depends on dynamic ensembles, but atomistic ensemble determination is still difficult despite advances in AI structure prediction.
• What they did: The framework was extended to AlphaFold2, AlphaFold3, Boltz-1, Boltz-2, ESMFold, and ESMFold2, comparing inter-residue distance distributions from each predictor and using bAIes to build ensembles.
• The result: Ensembles produced with bAIes show comparable accuracy to experimental NMR and SAXS data and competitive performance versus state-of-the-art all-atom simulations and other IDP ensemble methods, indicating robustness to predictor choice.

AI summary of the abstract · may contain errors · not medical advice · read the paper.